Related Experiment Video
Updated: Jun 27, 2026
12:55
Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
Published on: September 27, 2020
8.3K
Question-based computational language approach outperform ratings scale in discriminating between anxiety and
Mona Tabesh1, Mariam Mirström2, Rebecca Astrid Böhme2
1University of Milan-Bicocca, Italy.
Journal of Anxiety Disorders
|April 25, 2025
Summary
Question-based computational language assessment (QCLA) shows promise for diagnosing depression and anxiety. Autobiographical narratives and descriptive keywords can outperform traditional rating scales in identifying these mental health conditions.
Area of Science:
- Computational linguistics
- Mental health assessment
- Natural Language Processing (NLP)
Background:
- Major Depression (MD) and General Anxiety Disorder (GAD) are prevalent mental health conditions.
- Current assessments rely on quantitative rating scales like PHQ-9 and GAD-7.
- Advances in NLP and ML enable new approaches like Question-based Computational Language Assessment (QCLA).
Purpose of the Study:
- To investigate the accuracy of QCLA using open-ended questions in discriminating between individuals with self-reported depression, anxiety, and healthy controls.
- To compare the efficacy of QCLA measures (descriptive keywords, autobiographical narratives) against traditional rating scales (PHQ-9, GAD-7).
Main Methods:
- Utilized open-ended questions, including descriptive keywords and autobiographical narratives, for language-based assessment.
- Employed machine learning (ML) to analyze both QCLA data and individual items from PHQ-9 and GAD-7 rating scales.
- Calculated discrimination measures (phi coefficient, ϕ) to evaluate the performance of different assessment methods.
Main Results:
- Autobiographical narratives demonstrated the highest discrimination between healthy individuals and those with anxiety (ϕ = 1.58) and depression (ϕ = 1.38).
- Descriptive keywords and narratives often outperformed summed scores of GAD-7 and PHQ-9 (ϕ=0.80).
- ML analysis of individual scale items showed strong discrimination (PHQ-9: ϕ=0.86, GAD-7: ϕ=0.91), with combined scales further improving discrimination (ϕ=1.39).
Conclusions:
- QCLA measures, particularly autobiographical narratives, show significant potential for assessing depression and anxiety.
- While QCLA can be superior to traditional scales, ML analysis of individual scale items and combined scale approaches also yield high discrimination.
- These findings suggest QCLA offers a valuable, sometimes more effective, alternative or supplement to existing mental health assessment tools.
Related Concept Videos
01:30Generalized Anxiety Disorder
Generalized Anxiety Disorder (GAD) is a chronic condition characterized by excessive and uncontrollable worry that persists for at least six months, significantly interfering with daily functioning. Unlike situational anxiety, which arises in response to specific stressors, GAD often occurs without a clear cause. Individuals may experience disproportionate worry about work, health, or relationships. For instance, a person might continuously fear poor health despite normal medical evaluations or...
01:29Self-Discrepancy and Its Effects
Self-discrepancy theory explains how people compare their actual self to their ideal and ought selves and how mismatches between these self-guides can lead to emotional distress. Developed by E. Tory Higgins, the theory distinguishes among three components of self-concept: the actual self, the ideal self, and the ought self. These refer respectively to how individuals perceive themselves, how they aspire to be, and how they believe they are obligated to be. Emotional well-being, self-esteem,...